dataset_name = "openswe-reviewer-v1"
experiment_prefix = "openswe-review-confidence"
max_concurrency = 5

# LangSmith tracing project for eval runs. Keeps eval traces out of the
# deployment's production project.
langsmith_project = "open-swe-evals"

# Leave blank to use LANGGRAPH_URL or local dev.
langgraph_url = ""
assistant_id = "reviewer"
# models (post Bedrock/Fireworks migration): bedrock_converse:us.anthropic.claude-opus-4-8,
# or any fireworks:* id in agent/dashboard/options.py SUPPORTED_MODELS.
model_id = "bedrock_converse:us.anthropic.claude-opus-4-8"
reasoning_effort = "medium"

# score_mode:
# - "all_findings" — diagnostic mode for deduplicated add_finding calls.
# - "surfaced_findings" — score the exact final eval publication snapshot.
score_mode = "surfaced_findings"
severity_threshold = "low"
cap = 6